Foreground Object Detection in Complex Scenes Using Cluster Color

In visual surveillance systems, the image foreground object detection must face the problems of moving backgrounds, illumination changes, chaotic scenes, etc. in real word applications. The most used and accurate methods are mostly pixel-based, taking up more memory and requiring longer execution time. This paper presents a cluster color background model that possesses efficient processing and low memory requirement in complex scenes. Our proposed approach consumes 32.5% less memory and increases accuracy by at least 2.5% compared to other existing methods. Last, implementing the object detection algorithm on the 2.83GHz CPU, we can achieve 26 frames per second for the benchmark video with image size 768×576.